Back to Publications

Author(s) Roziere, B., Carraz Rakotonirina, N., Hosu, V., Rasoanaivo, A., Lin, H., Couprie, C., Teytaud, O.
Title Tarsier: Evolving noise injection in super-resolution GANs
Abstract Super-resolution aims at increasing the resolution and level of detail within an image. The current state of the art in general single-image super-resolution is held by NESRGAN+, which injects a Gaussian noise after each residual layer at training time. In this paper, we harness evolutionary methods to improve NESRGAN+ by optimizing the noise injection at inference time. More precisely, we use Diagonal CMA to optimize the injected noise according to a novel criterion combining quality assessment and realism. Our results are validated by the PIRM perceptual score and a human study. Our method outperforms NESRGAN+ on several standard super-resolution datasets. More generally, our approach can be used to optimize any method based on noise injection.
Download RoCaHo21.pdf